perf tools: Allow all_cpus to be a superset of user_requested_cpus

To support collection of system-wide events with user requested CPUs,
all_cpus must be a superset of user_requested_cpus.

In order to support all_cpus to be a superset of user_requested_cpus,
all_cpus must be used instead of user_requested_cpus when dealing with CPUs
of all events instead of CPUs of requested events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Link: https://lore.kernel.org/r/20220524075436.29144-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index ed66f2e..ec0e4b5 100644 (file)
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -298,7 +298,7 @@ add:
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-       int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
+       int nr_cpus = perf_cpu_map__nr(evlist->all_cpus);
        int nr_threads = perf_thread_map__nr(evlist->threads);
        int nfds = 0;
        struct perf_evsel *evsel;
@@ -430,7 +430,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
               int idx, struct perf_mmap_param *mp, int cpu_idx,
               int thread, int *_output, int *_output_overwrite)
 {
-       struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
+       struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx);
        struct perf_evsel *evsel;
        int revent;
 
@@ -540,7 +540,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
             struct perf_mmap_param *mp)
 {
        int nr_threads = perf_thread_map__nr(evlist->threads);
-       int nr_cpus    = perf_cpu_map__nr(evlist->user_requested_cpus);
+       int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);
        int cpu, thread;
 
        for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -565,8 +565,8 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 {
        int nr_mmaps;
 
-       nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus);
-       if (perf_cpu_map__empty(evlist->user_requested_cpus))
+       nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
+       if (perf_cpu_map__empty(evlist->all_cpus))
                nr_mmaps = perf_thread_map__nr(evlist->threads);
 
        return nr_mmaps;
@@ -577,7 +577,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
                          struct perf_mmap_param *mp)
 {
        struct perf_evsel *evsel;
-       const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
+       const struct perf_cpu_map *cpus = evlist->all_cpus;
 
        if (!ops || !ops->get || !ops->mmap)
                return -EINVAL;

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c8a79f3..cf9a7ce 100644 (file)
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -967,14 +967,20 @@ static void record__thread_data_close_pipes(struct record_thread *thread_data)
        }
 }
 
+static bool evlist__per_thread(struct evlist *evlist)
+{
+       return cpu_map__is_dummy(evlist->core.user_requested_cpus);
+}
+
 static int record__thread_data_init_maps(struct record_thread *thread_data, struct evlist *evlist)
 {
        int m, tm, nr_mmaps = evlist->core.nr_mmaps;
        struct mmap *mmap = evlist->mmap;
        struct mmap *overwrite_mmap = evlist->overwrite_mmap;
-       struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
+       struct perf_cpu_map *cpus = evlist->core.all_cpus;
+       bool per_thread = evlist__per_thread(evlist);
 
-       if (cpu_map__is_dummy(cpus))
+       if (per_thread)
                thread_data->nr_mmaps = nr_mmaps;
        else
                thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
@@ -995,7 +1001,7 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
                 thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);
 
        for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) {
-               if (cpu_map__is_dummy(cpus) ||
+               if (per_thread ||
                    test_bit(perf_cpu_map__cpu(cpus, m).cpu, thread_data->mask->maps.bits)) {
                        if (thread_data->maps) {
                                thread_data->maps[tm] = &mmap[m];
@@ -1870,7 +1876,7 @@ static int record__synthesize(struct record *rec, bool tail)
                return err;
        }
 
-       err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus,
+       err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.all_cpus,
                                             process_synthesized_event, NULL);
        if (err < 0) {
                pr_err("Couldn't synthesize cpu map.\n");
@@ -3668,12 +3674,12 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
 static int record__init_thread_masks(struct record *rec)
 {
        int ret = 0;
-       struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus;
+       struct perf_cpu_map *cpus = rec->evlist->core.all_cpus;
 
        if (!record__threads_enabled(rec))
                return record__init_thread_default_masks(rec, cpus);
 
-       if (cpu_map__is_dummy(cpus)) {
+       if (evlist__per_thread(rec->evlist)) {
                pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n");
                return -EINVAL;
        }

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ac4e466..511dd3c 100644 (file)
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -181,7 +181,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
        mp->idx = idx;
 
        if (per_cpu) {
-               mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx);
+               mp->cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
                if (evlist->core.threads)
                        mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
                else